What can NVIDIA RTX PRO 6000 Blackwell run?

Build: RTX PRO 6000 Blackwell + Threadripper PRO + 128GB

Memory: 96 GB VRAM + 128 GB system RAM
Runner: llama.cpp / Ollama (CUDA)

Runs comfortably
264 models

Full-VRAM resident, with room for context. No compromises.

#1Qwen 3 0.6B
0.6B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 93.6 GB
3215
tok/s
Estimated
Weights
0.30 GB
KV cache
0.30 GB
Activations
0.02 GB
Runtime
1.80 GB
#2Llama 4 Scout
109B
llama
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 83.7 GBHeadroom: 12.3 GB
ollama run llama4:scout
18
tok/s
Estimated
Weights
65.00 GB
KV cache
13.63 GB
Activations
3.25 GB
Runtime
1.80 GB
#3Llama 3.1 8B Instruct
8B
llama
Commercial OK
Quant: FP16Context: 8,192VRAM: 19.8 GBHeadroom: 76.2 GB
ollama run llama3.1:8b
73
tok/s
Estimated
Weights
16.10 GB
KV cache
1.07 GB
Activations
0.81 GB
Runtime
1.80 GB
#4Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 50.4 GBHeadroom: 45.6 GB
ollama run qwen3:30b
37
tok/s
Estimated
Weights
32.00 GB
KV cache
15.00 GB
Activations
1.61 GB
Runtime
1.80 GB
#5Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 39.7 GBHeadroom: 56.3 GB
ollama run qwen2.5-coder:32b
34
tok/s
Estimated
Weights
34.00 GB
KV cache
2.15 GB
Activations
1.71 GB
Runtime
1.80 GB
#6Qwen3.6 27B
27B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 33.2 GBHeadroom: 62.8 GB
ollama run qwen3.6:27b
71
tok/s
Estimated
Weights
17.00 GB
KV cache
13.50 GB
Activations
0.86 GB
Runtime
1.80 GB
#7Llama 3.3 70B Instruct
70B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 78.0 GBHeadroom: 18.0 GB
ollama run llama3.3:70b
16
tok/s
Estimated
Weights
70.00 GB
KV cache
2.68 GB
Activations
3.51 GB
Runtime
1.80 GB
#8Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 53.5 GBHeadroom: 42.5 GB
ollama run qwen3:32b
34
tok/s
Estimated
Weights
34.00 GB
KV cache
16.00 GB
Activations
1.71 GB
Runtime
1.80 GB
#9Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 52.0 GBHeadroom: 44.0 GB
ollama run gemma4:31b
35
tok/s
Estimated
Weights
33.00 GB
KV cache
15.50 GB
Activations
1.66 GB
Runtime
1.80 GB
#10Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.4 GBHeadroom: 81.6 GB
ollama run qwen3:8b
137
tok/s
Estimated
Weights
8.20 GB
KV cache
4.00 GB
Activations
0.42 GB
Runtime
1.80 GB
#11Gemma 4 12B
12B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 15.8 GBHeadroom: 80.2 GB
ollama run gemma4:12b
161
tok/s
Estimated
Weights
7.60 GB
KV cache
6.00 GB
Activations
0.39 GB
Runtime
1.80 GB
#12Qwen3.5 9B
9B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 13.2 GBHeadroom: 82.8 GB
ollama run qwen3.5:9b
214
tok/s
Estimated
Weights
6.60 GB
KV cache
4.50 GB
Activations
0.34 GB
Runtime
1.80 GB

Runs with tradeoffs
12 models

Tight VRAM, partial CPU offload, or context-limited.

GLM-5
200B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 152.8 GBHeadroom: 20.0 GB
  • Partial CPU offload: ~37% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3
tok/s
Estimated
Weights
120.00 GB
KV cache
25.00 GB
Activations
6.00 GB
Runtime
1.80 GB
Nemotron 3 Super (120B-A12B)
120B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 92.4 GBHeadroom: 3.6 GB
  • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run nemotron3:super
16
tok/s
Estimated
Weights
72.00 GB
KV cache
15.00 GB
Activations
3.60 GB
Runtime
1.80 GB
Quant: Q4_K_MContext: 2,048VRAM: 93.8 GBHeadroom: 2.2 GB
  • Tight VRAM fit — only 2.2 GB headroom left for context growth
ollama run mistral-large:123b
16
tok/s
Estimated
Weights
73.00 GB
KV cache
15.38 GB
Activations
3.65 GB
Runtime
1.80 GB
Mixtral 8x22B Instruct
141B
mixtral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 160.5 GBHeadroom: 12.3 GB
  • Partial CPU offload: ~40% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run mixtral:8x22b
5
tok/s
Estimated
Weights
84.00 GB
KV cache
70.50 GB
Activations
4.21 GB
Runtime
1.80 GB
WizardLM-2 8x22B
141B
wizard
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 160.5 GBHeadroom: 12.3 GB
  • Partial CPU offload: ~40% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
5
tok/s
Estimated
Weights
84.00 GB
KV cache
70.50 GB
Activations
4.21 GB
Runtime
1.80 GB
Quant: Q4_K_MContext: 2,048VRAM: 167.6 GBHeadroom: 5.2 GB
  • Partial CPU offload: ~43% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3
tok/s
Estimated
Weights
129.80 GB
KV cache
29.50 GB
Activations
6.49 GB
Runtime
1.80 GB
Kimi K1.5
200B
moonshot
Quant: AWQ-INT4Context: 2,048VRAM: 147.6 GBHeadroom: 25.2 GB
  • Partial CPU offload: ~35% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
2
tok/s
Estimated
Weights
115.00 GB
KV cache
25.00 GB
Activations
5.75 GB
Runtime
1.80 GB
DBRX Base
132B
dbrx
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 146.6 GBHeadroom: 26.2 GB
  • Partial CPU offload: ~34% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
20
tok/s
Estimated
Weights
75.00 GB
KV cache
66.00 GB
Activations
3.76 GB
Runtime
1.80 GB

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

+32 GB system RAM

~$80–150

Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 14 new tradeoff

  • Qwen 3 235B-A22B
  • GLM-5
  • Nemotron 3 Super (120B-A12B)
  • Llama 3.1 Nemotron Ultra 253B

Upgrade to NVIDIA H200 NVL (PCIe)

~$32000

141 GB VRAM (vs your 96 GB) plus a bandwidth jump from ~1792 GB/s to ~4800 GB/s.

Unlocks: 5 new comfortable

  • Mixtral 8x22B Instruct
  • WizardLM-2 8x22B
  • DBRX Base
  • DBRX Instruct

Add a second NVIDIA RTX PRO 6000 Blackwell

~$8999

Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.

Unlocks: 14 new comfortable

  • Qwen 3 235B-A22B
  • GLM-5
  • Nemotron 3 Super (120B-A12B)
  • Llama 3.1 Nemotron Ultra 253B

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)
1600B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.

Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.

Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.

DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.

DeepSeek V4 Flash (284B MoE)
284B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.

How to read these numbers

Measured here
Measured here - RunLocalAI ran this exact combo on owner hardware with public evidence.

Source-backed
Source-backed / community - a reproduced public source supports the speed, but it is not labeled as owner-measured.

Extrapolated
Extrapolated - predicted from a measured benchmark on similar-bandwidth hardware.

Estimated
Estimated - formula based on VRAM bandwidth and model architecture; not a benchmark row.

RunLocalAI Will-It-Run Framework →

Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.